arXiv:2604.07019v1 Announce Type: cross Abstract: Neural networks deliver impressive predictive performance across a variety of tasks, but they are often opaque in their decision-making processes. Despite a growing interest in mechanistic interpretability, tools for systematically exploring the representations learned by neural networks in general, and tabular foundation models in particular, remain limited. In this work, […]
Plasma GraphRAG: Physics-Grounded Parameter Selection for Gyrokinetic Simulations
arXiv:2604.06279v1 Announce Type: cross Abstract: Accurate parameter selection is fundamental to gyrokinetic plasma simulations, yet current practices rely heavily on manual literature reviews, leading to inefficiencies and inconsistencies. We introduce Plasma GraphRAG, a novel framework that integrates Graph Retrieval-Augmented Generation (GraphRAG) with large language models (LLMs) for automated, physics-grounded parameter range identification. By constructing a […]
Beyond Surface Judgments: Human-Grounded Risk Evaluation of LLM-Generated Disinformation
arXiv:2604.06820v1 Announce Type: new Abstract: Large language models (LLMs) can generate persuasive narratives at scale, raising concerns about their potential use in disinformation campaigns. Assessing this risk ultimately requires understanding how readers receive such content. In practice, however, LLM judges are increasingly used as a low-cost substitute for direct human evaluation, even though whether they […]
SurFITR: A Dataset for Surveillance Image Forgery Detection and Localisation
arXiv:2604.07101v1 Announce Type: cross Abstract: We present the Surveillance Forgery Image Test Range (SurFITR), a dataset for surveillance-style image forgery detection and localisation, in response to recent advances in open-access image generation models that raise concerns about falsifying visual evidence. Existing forgery models, trained on datasets with full-image synthesis or large manipulated regions in object-centric […]
TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models
arXiv:2604.06291v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning of Large Language Models (LLMs), and recent Mixture-of-Experts (MoE) extensions further enhance flexibility by dynamically combining multiple LoRA experts. However, existing MoE-augmented LoRA methods assume that experts operate independently, often leading to unstable routing, expert dominance. In this paper, we propose textbfTalkLoRA, a communication-aware […]
WebCVTree4: A Newly Designed Phylogenetic and Taxonomic Study Platform for Prokaryotes Using Composition Vectors and Whole Genomes
arXiv:2604.06835v1 Announce Type: new Abstract: CVTree is an alignment-free methodology for inferring species phylogeny and taxonomy. This method allows for the efficient and accurate resolution of evolutionary relationships among large numbers of species based on whole-genome sequence data. Since 2004, we have been continuously providing CVTree web services. Recently, the server has undergone a significant […]
Dynamic Context Evolution for Scalable Synthetic Data Generation
arXiv:2604.07147v1 Announce Type: cross Abstract: Large language models produce repetitive output when prompted independently across many batches, a phenomenon we term cross-batch mode collapse: the progressive loss of output diversity when a language model is prompted repeatedly without access to its prior generations. Practitioners have long mitigated this with ad hoc deduplication and seed rotation, […]
Do We Need Distinct Representations for Every Speech Token? Unveiling and Exploiting Redundancy in Large Speech Language Models
arXiv:2604.06871v1 Announce Type: cross Abstract: Large Speech Language Models (LSLMs) typically operate at high token rates (tokens/s) to ensure acoustic fidelity, yet this results in sequence lengths that far exceed the underlying semantic content, incurring prohibitive inference costs. In this paper, we empirically revisit the necessity of such granular token-level processing. Through layer-wise oracle interventions, […]
AgentOpt v0.1 Technical Report: Client-Side Optimization for LLM-Based Agent
arXiv:2604.06296v1 Announce Type: cross Abstract: AI agents are increasingly deployed in real-world applications, including systems such as Manus, OpenClaw, and coding agents. Existing research has primarily focused on emphserver-side efficiency, proposing methods such as caching, speculative execution, traffic scheduling, and load balancing to reduce the cost of serving agentic workloads. However, as users increasingly construct […]
Spectral Edge Dynamics Reveal Functional Modes of Learning
arXiv:2604.06256v1 Announce Type: cross Abstract: Training dynamics during grokking concentrate along a small number of dominant update directions — the spectral edge — which reliably distinguishes grokking from non-grokking regimes. We show that standard mechanistic interpretability tools (head attribution, activation probing, sparse autoencoders) fail to capture these directions: their structure is not localized in parameter […]
ClawLess: A Security Model of AI Agents
arXiv:2604.06284v1 Announce Type: cross Abstract: Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to regulate agent behavior through training or prompting, which does not offer fundamental security guarantees. We present ClawLess, […]
Quantitative Estimation of Target Task Performance from Unsupervised Pretext Task in Semi/Self-Supervised Learning
arXiv:2508.07299v2 Announce Type: replace-cross Abstract: The effectiveness of unlabeled data in Semi/Self-Supervised Learning (SSL) depends on appropriate assumptions for specific scenarios, thereby enabling the selection of beneficial unsupervised pretext tasks. However, existing research has paid limited attention to assumptions in SSL, resulting in practical situations where the compatibility between the unsupervised pretext tasks and the […]